NDTnet 1998 Aug, Vol.3 No.8

Abstract

Pattern recognition of artificial neural network is being applied for some waveform data. The data were taken from acoustic emission monitoring of pressure vessels and underground pipelines, from acousto-ultrasonic testing of composite materials. The characteristic data for the input of neural network were obtained from original waveform data by the various methods respecting to the different individual data characteristics The preprocessing methods include some advanced modem spectrum analysis methods. The neural networks are basically BP networks with some significant modifications such as single data group training for the data type of shortage of good quality data.

Abstract Source:
Book of Abstracts, 7th European Conference on Non-Destructive Testing, 26-29 May 1998, ISBN: 87-986898-0-00

Full-Text Source:
Proceedings of the 7th European Conference on Non-Destructive Testing, 26-29 May 1998, ISBN:

Publication Contact:
7th ECNDT, Park Alle 345, DK-2605 Broendby, Denmark, Fax: +45 46 26 70 11, Email: 101373.3414@compuserve.com